DocumentCode :
1696442
Title :
Modeling and analysis of task migration in shared-memory multiprocessor computer systems
Author :
Nelson, Randolph D. ; Squillante, Mark S.
Author_Institution :
OTA Ltd. Partnership, Purchase, NY, USA
fYear :
1996
Firstpage :
262
Lastpage :
266
Abstract :
In this paper we study a tradeoff between keeping the system workload balanced and scheduling tasks where they run most efficiently in shared-memory multiprocessor commercial environments. We formulate a general model of receiver-initiated task migration and derive a mathematical analysis of the model. Our results yield insights and information that can be used to design and develop adaptive scheduling policies for high-performance computing and telecommunication systems
Keywords :
processor scheduling; resource allocation; scheduling; shared memory systems; adaptive scheduling; high-performance computing; scheduling tasks; shared-memory multiprocessor; system workload; task migration; Adaptive scheduling; Computer architecture; Costs; Mathematical analysis; Mathematical model; Multiprocessing systems; Processor scheduling; System performance; Telecommunication computing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, 1996. MASCOTS '96., Proceedings of the Fourth International Workshop on
Conference_Location :
San Jose, CA
Print_ISBN :
0-8186-7235-8
Type :
conf
DOI :
10.1109/MASCOT.1996.501028
Filename :
501028
Link To Document :
بازگشت